Is the Reliability of Objective Originality Scores Confounded by Elaboration?

<p>The increased use of text-mining models as a scoring mechanism for divergent thinking (DT) tasks has sparked concerns about the ways in which automated Originality scores may be influenced by other dimensions of DT, especially Elaboration. The debate centers around the question of whether too much variance in automated Originality scores is accounted for by the number of words a participant uses in a response (i.e., Elaboration), and, thus, how the influence of Elaboration can affect the reliability of Originality scores. Here, a partial correlation analysis, in conjunction with text-mining and psychometric modeling, is conducted to test the degree to which the reliability of Originality scores produced via a freely-available text-mining system is dependent on the variance explained by Elaboration. Findings reveal that, when modern methodological recommendations for text-mining Originality scoring are applied, the reliability of Originality scores estimated by the GloVe 840B text-mining system is not meaningfully confounded by Elaboration. I conclude that, even when the variance attributed to Elaboration is partialled out, this method is capable of providing reliable Originality scores.</p>

Name thesis:degree_name

M.A.

Level thesis:degree_level

Masters Thesis

Year dc:date.available

2020

Author dc:creator

• Maio, Shannon Marie

Contributors dc:contributor

• Denis Dumas
• Peter Organisciak
• Garrett Roberts
• Jesse Owen

• Divergent thinking
• Elaboration
• Originality
• Reliability
• Text-mining model
• Psychology
• Statistical Methodology
• Statistics and Probability

Statement dc:rights

• <p>Copyright is held by the author. User is responsible for all copyright compliance.</p>

Language dc:language

en

Repository record dc:identifier

https://digitalcommons.du.edu/etd/1795

OAI identifier oai:identifier

oai:digitalcommons.du.edu:etd-2795